paper-with-me

Papers

CoMotion: Concurrent Multi-person 3D Motion

2025-04-16 · Alejandro Newell, Peiyun Hu, Lahav Lipson, Stephan R. Richter, Vladlen Koltun

We introduce an approach for detecting and tracking detailed 3D poses of multiple people from a single monocular camera stream. Our system maintains temporally coherent predictions in crowded scenes filled with difficult poses and occlusions. Our model performs both strong per-frame detection and a learned pose update to track people from frame to frame. Rather than match detections across time, poses are updated directly from a new input image, which enables online tracking through occlusion. We train on numerous image and video datasets leveraging pseudo-labeled annotations to produce a model that matches state-of-the-art systems in 3D pose estimation accuracy while being faster and more accurate in tracking multiple people through time. Code and weights are provided at https://github.com/apple/ml-comotion

📄 PDF Abstract BibTeX arXiv:2504.12186

Code (1)

apple/ml-comotion 공식 구현 pytorch

Tasks

3D Pose EstimationPose Estimation

Similar Papers 제목 키워드 기반

Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior

2023-10-02 · Ruihan Yang, Zhuoqun Chen, Jianhan Ma, Chongyi Zheng 외

The agility of animals, particularly in complex activities such as running, turning, jumping, and backflipping, stands as an exemplar for robotic system design. Transferring this suite of behaviors to legged robotic syst…

StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion

2025-03-19 · Le Ma, Ziyu Meng, Tengyu Liu, Yuhan Li 외

Humanoid robots are anticipated to acquire a wide range of locomotion capabilities while ensuring natural movement across varying speeds and terrains. Existing methods encounter a fundamental dilemma in learning humanoid…

Imitation Learningreinforcement-learningReinforcement Learning

Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion

2022-02-11 · Gwanghyeon Ji, Juhyeok Mun, Hyeongjun Kim, Jemin Hwangbo

In this paper, we propose a locomotion training framework where a control policy and a state estimator are trained concurrently. The framework consists of a policy network which outputs the desired joint positions and a …

FrictionState Estimation

Dynamics Aware Quadrupedal Locomotion via Intrinsic Dynamics Head

2026-05-02 · Aman Arora, Nalini Ratha arxiv

Quadrupedal locomotion plays a critical role in enabling agile, versatile movement across complex terrains. Understanding and estimating the underlying physical dynamics are essential for achieving efficient and stable q…

Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking

2026-04-19 · Zewei Zhang, Kehan Wen, Michael Xu, Junzhe He 외 arxiv

Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard perception. Directly applying reinforcemen…

Reinforcement Learning